AI model SORA – Open AI’s new launch to turn AI prompts into Photorealistic Videos

AI Model SORA – Latest internet sensation

AI Model SORA – Within few hours of the official introduction of Sora (openai.com/sora) by Open AI on 15 Feb – new AI model that is capable of turning text into photo-realistic videos, it has become internet sensation globally in the world of Artificial Intelligence. As per Open AI, Sora is an AI model that can create realistic and imaginative scenes from text instructions.

AI Model SORA – POC shared through several text to videos models by AI prompts

AI Model Sora proof of concept was shared by Open AI with the help of several videos that got generated by use of AI Prompts. With the launch of AI Model Sora, Open AI has shared several proof of concepts with AI prompts that converts the text into a video.

As per Open AI, AI Model Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.

In a video shared through above link, following text Prompt had been used:

“Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes.”

AI Model SORA – Detailed technical report is shared by Open AI for AI enthusiasts

With the launch, a technical report has been shared by Open AI. Sora can sample widescreen 1920x1080p videos, vertical 1080×1920 videos and everything inbetween. This lets Sora create content for different devices directly at their native aspect ratios. It also lets us quickly prototype content at lower sizes before generating at full resolution—all with the same model.

As per Open AI, there will be several important safety steps ahead of making Sora available in OpenAI’s products. Open AI is working with red teamers — domain experts in areas like misinformation, hateful content, and bias — who are adversarially testing the model.

Similarly, in another beautiful video that was shared shows giant wooly elephants treading on snowy meadow through another text prompt, “Several giant wooly mammoths approach treading through a snowy meadow, their long wooly fur lightly blows in the wind as they walk, snow covered trees and dramatic snow capped mountains in the distance, mid afternoon light with wispy clouds and a sun high in the distance creates a warm glow, the low camera view is stunning capturing the large furry mammal with beautiful photography, depth of field.”

So far, at twitter alone, 3.1M views has been done for this 10 seconds video generated by AI Model Sora.

AI Model SORA – Attracted media and public attention with mixed reviews

AI Model SORA gained attraction from world-wide media. Some media houses stressed upon a fact that other companies like Google through AI Gemini and startups like Runway, have already revealed such AI prompts that can convert text into videos. However, they appreciated AI Model SORA claim for 60-seconds long photorealistic video generation capability, with a note that the longest video shared as of now was for 17-seconds. Some experts also commented about the quality of the video highlighting the point that they are able to make out that the video was digitally artificially generated.

Users of X commented to share how they feel after looking at AI Model Sora capabilities. Some of the comments read like:

• AI is making me feel i’m wasting my time studying arts. At this point I fear my future is gonna be affected by this medium, the fact that this fear is getting stronger with each new i see about AI “progressing”sickens me, and I’m sure I’m not the only one.
• Sensible people will continue to see the irreplaceable value of human made art. And with all the ways tools like this can be abused ai regulations are inevitable.
• Within a couple years, we will be watching regular movies fully made by AI
• Not only is it that this could definitely make many jobs disappear, but the integrity of many people could be at risk, fake news, CP, violence content this definitely should have regulation.
• Find better jobs. Ya’ll have had it too easy sitting on your ass all day and earning more than your deserve. God forbid you actually had to do a 9 to 5 job

AI Model SORA – Not available for public, no timeline shared

AI Model SORA is not yet available for the use by public and Open AI did not shared any timeline by when this can be expected, however, it is highly expected to be roll-out in 2024 itself. As per Open AI, Sora is currently being put through its paces by security researchers who are responsible for ensuring it’s safe and secure before it’s released to the public, and assessing “critical risks”. However, OpenAI says that a small cohort of visual artists, filmmakers, and designers have been given access to Sora too.

It is expected that AI Model SORA whenever is made available to public will be free to use same like Google Cloud offers free usage of many AI products up to monthly limits, including Translation, Speech-to-Text, Natural Language, and Video Intelligence. There is no charge to use these products up to their specified free usage limit.

Notably, on 15 Feb Google had also introduced Gemini 1.5 pro, a next-generation AI model. It shows dramatically enhanced performance, including long-context understanding across modalities, which opens up new possibilities for people to create and build with AI. This advanced model is designed to handle larger volumes of text and video compared to its competitors, marking a significant leap forward in the realm of generative AI.

Open AI is also working to improve ChatGPT

Open AI has shared that they are working to improve the user experience on ChatGPT by building remembrance abilities. View and delete memories or turn the feature off altogether will also be available as part of the user-settings.